AI Platform Engineer — Kubernetes, GitOps & Cloud Infra

INTEGRATION APPLIANCE; New York (NY); On-site; USD 140,000 - 190,000; Full time

Job summary

INTEGRATION APPLIANCE is seeking a seasoned Platform Engineer to operate a Kubernetes-based AI workloads platform. You will drive IaC, GitOps, and multi-cloud model hosting while ensuring security and observability.

You will collaborate with product teams, implement OpenTelemetry, and optimize costs across AWS/Azure. The role offers a collaborative culture and meaningful impact in a growing team.

Qualifications

• 3+ years in platform, DevOps, SRE, or cloud engineering.
• Hands-on Kubernetes with deployments, networking, and troubleshooting.
• IaC (Terraform) and GitOps tooling (Argo CD, Flux or similar).
• Experience with at least one major cloud (Azure or AWS).
• Observability tools such as OpenTelemetry, Prometheus, Grafana; scripting in Python/Go/Bash; CI/CD experience.

Responsibilities

• Operate and evolve a Kubernetes-based AI workloads platform, including LLM gateways and agent runtimes.
• Integrate and manage access to cloud-hosted foundation models across providers with routing, quotas, fallbacks, cost controls, and isolation.
• Deliver infrastructure as code and GitOps workflows.
• Build monitoring, alerting, and tracing for AI workloads.
• Help design self-hosted model serving, including GPU workloads and inference runtimes.
• Harden the platform with secrets management, network policies, authz, and audit logging.
• Support internal product teams with documentation, onboarding, and troubleshooting.

Skills

DevOps practices

SRE mindset

Multi-cloud experience

Networking troubleshooting

Tools

Kubernetes

Terraform

Argo CD

Flux

OpenTelemetry

Prometheus

Grafana

Python

Go

Bash

CI/CD

Azure

AWS

Job description

INTEGRATION APPLIANCE is seeking a seasoned Platform Engineer to operate a Kubernetes-based AI workloads platform. You will drive IaC, GitOps, and multi-cloud model hosting while ensuring security and observability.

You will collaborate with product teams, implement OpenTelemetry, and optimize costs across AWS/Azure. The role offers a collaborative culture and meaningful impact in a growing team.